Bootstrap Your Own Variance
Journal ref NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice
期刊&会议
NeurIPS
Conference on Neural Information Processing Systems · 会议 · Machine Learning
Data-Driven Traffic Reconstruction and Kernel Methods for Identifying Stop-and-Go Congestion
Comments Presented at NeurIPS 2023 workshops: Tackling Climate Change with Machine Learning & Computational Sustainability
SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction
Comments Accepted to the Advances in Neural Information Processing Systems (Datasets and Benchmarks Track) 2023
Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence
Comments Accepted by the AI for Science (AI4Science) Workshop and the New Frontiers of AI for Drug Discovery and Development (AI4D3) Workshop at NeurIPS 2023
The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch
Comments Accepted at NeurIPS 2023 Workshop on Distribution Shifts; 4 pages + appendix; proposed data set at https://jzenn.github.io/svhn-remix/
Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback
Journal ref Published at NeurIPS 2023
Delegated Classification
Comments Accepted for publication in NeurIPS 2023
$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning
Journal ref Thirty-seventh Conference on Neural Information Processing Systems, Dec 2023, New Orleans, United States
The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
Comments NeurIPS 2023 (Oral)
Feature-Learning Networks Are Consistent Across Widths At Realistic Scales
Comments 24 pages, 19 figures. NeurIPS 2023. Revised based on reviewer feedback
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Comments Accepted to NeurIPS 2023 (spotlight). Project website: https://swiftsage.github.io
Coherent Soft Imitation Learning
Comments 51 pages, 49 figures. DeepMind internship report. Accepted as a spotlight paper at Advances in Neural Information Processing Systems 2023
ReSync: Riemannian Subgradient-based Robust Rotation Synchronization
Comments Accepted for publication in NeurIPS 2023
Continual Learning for Instruction Following from Realtime Feedback
Comments NeurIPS 2023 Spotlight paper
Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection
Comments Accepted in NeurIPS 2023. Code is available at https://github.com/luluho1208/Diffusion-SS3D
Rare Galaxy Classes Identified In Foundation Model Representations
Comments Accepted at Machine Learning and the Physical Sciences Workshop, NeurIPS 2023
Deep Learning Segmentation of Spiral Arms and Bars
Comments Accepted at Machine Learning and the Physical Sciences Workshop, NeurIPS 2023
Attention-enhanced neural differential equations for physics-informed deep learning of ion transport
Comments 8 pages, 2 figures. Accepted in the NeurIPS Machine Learning and the Physical Sciences Workshop
Lessons from Usable ML Deployments and Application to Wind Turbine Monitoring
Comments Presented in XAI in Action: Past, Present, and Future Applications @ NeurIPS 2023. 8 pages, 3 figures
Expert-guided Bayesian Optimisation for Human-in-the-loop Experimental Design of Known Systems
Comments NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World. Main text: 6 pages
Are Vision Transformers More Data Hungry Than Newborn Visual Systems?
Comments Accepted in Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023)
MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition
Comments accepted in NeurIPS 2023
Scaling-up Memristor Monte Carlo with magnetic domain-wall physics
Comments Presented at the 1st workshop on Machine Learning with New Compute Paradigms (MLNCP) at NeurIPS 2023 (New Orleans, USA)
Towards Measuring Representational Similarity of Large Language Models
Comments Extended abstract in UniReps Workshop @ NeurIPS 2023
Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models
Comments NeurIPS 2023
Simplifying Neural Network Training Under Class Imbalance
Comments NeurIPS 2023. Code available at https://github.com/ravidziv/SimplifyingImbalancedTraining
Fast non-autoregressive inverse folding with discrete diffusion
Comments NeurIPS Machine learning for Stuctural Biology workshop
Decoding Data Quality via Synthetic Corruptions: Embedding-guided Pruning of Code Data
Comments 12 pages, 4 figures, Oral Presentation at 3rd Workshop on Efficient Natural Language and Speech Processing (ENLSP-III), NeurIPS 2023
BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks
Comments NeurIPS 2023 Datasets and Benchmarks Oral. Dataset links are available on Github: https://github.com/minerllabs/basalt-benchmark
Approximation of Intractable Likelihood Functions in Systems Biology via Normalizing Flows
Comments NeurIPs 2023 Generative AI and Biology workshop paper
